adfa, p. 1, 2011. © Springer-Verlag Berlin Heidelberg 2011 Evaluation of English to Urdu Machine Translation Vaishali Gupta, Nisheeth Joshi, Iti Mathur Apaji Institute, Banasthali University, Rajasthan, India vaishali.gupta77@gmail.com, nisheeth.joshi@rediffmail.com, mathur_iti@rediffmail.com Abstract. This paper is based on the Evaluation of English to Urdu Machine Translation. Evaluation measures the quality characteristic of the Machine Translation out- put and is based on two approaches: Human Evaluation and Automatic Evalua- tion. In this paper, we are mainly concentrating over Human Evaluation. Machine Translation is an emerging research area in which human beings play a very crucial role. Since language is so vast and because of its diverse in na- ture, the accuracy is not maintained. To maintain this accuracy, Human Evalua- tion is taken as a base. Human Evaluation can be used with different parame- ters to judge the quality of sentences. Keywords: Human Evaluation, Adequacy, Fluency, Comprehensibility. 1 Introduction We live in a trans-lingual society where people from different linguistic back- grounds live together. It is practically impossible for an individual to speak all this languages. In this context MT proves to be a savior. In MT, research work totally depends on the result of its evaluation. Since Machine Translation is an automated system therefore it is not necessary that the system will pro- vide us the accurate result. To know the accuracy of the result, evaluation is required. We can evaluate any languages by two ways: Human Evaluation and Automatic Evaluation. In Human Evaluation, we have a source language and target language. These two languages are compared by an expert on the basis of some parameters. Since human is a valuable resource therefore it is costly and time consuming.